Search in sources :

Example 31 with Attribute

use of edu.uci.ics.texera.api.schema.Attribute in project textdb by TextDB.

the class SchemaTest method testGetAttribute.

@Test
public void testGetAttribute() {
    Attribute expectedAttribute1 = new Attribute("sampleAttribute_1", AttributeType.STRING);
    Attribute expectedAttribute2 = new Attribute("sampleAttribute_2", AttributeType.STRING);
    Attribute retrievedAttribute1 = schema.getAttribute(attributeName1);
    Attribute retrievedAttribute2 = schema.getAttribute(attributeName2.toUpperCase());
    Assert.assertEquals(expectedAttribute1, retrievedAttribute1);
    Assert.assertEquals(expectedAttribute2, retrievedAttribute2);
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Test(org.junit.Test)

Example 32 with Attribute

use of edu.uci.ics.texera.api.schema.Attribute in project textdb by TextDB.

the class SchemaTest method testAddingInBetween.

@Test(expected = UnsupportedOperationException.class)
public void testAddingInBetween() {
    // Should fail due to immutability
    List<Attribute> attributes = schema.getAttributes();
    attributes.add(0, new Attribute("sampleField_3", AttributeType.STRING));
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Test(org.junit.Test)

Example 33 with Attribute

use of edu.uci.ics.texera.api.schema.Attribute in project textdb by TextDB.

the class SpanTupleTest method testGetters.

@Test
public void testGetters() throws ParseException {
    // create data tuple first
    Attribute[] attributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length + 1];
    for (int count = 0; count < attributes.length - 1; count++) {
        attributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
    }
    attributes[attributes.length - 1] = SchemaConstants.SPAN_LIST_ATTRIBUTE;
    List<IField> fields = new ArrayList<IField>(Arrays.asList(new IField[] { new StringField("bruce"), new StringField("lee"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("bruce was born in new york city and was grown up in los angeles") }));
    IField spanField = createSpanListField();
    fields.add(spanField);
    spanTuple = new Tuple(new Schema(attributes), fields.toArray(new IField[fields.size()]));
    IField spanFieldRetrieved = spanTuple.getField(SchemaConstants.SPAN_LIST);
    Assert.assertTrue(spanFieldRetrieved instanceof ListField);
    Assert.assertSame(spanField, spanFieldRetrieved);
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) ListField(edu.uci.ics.texera.api.field.ListField) IField(edu.uci.ics.texera.api.field.IField) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 34 with Attribute

use of edu.uci.ics.texera.api.schema.Attribute in project textdb by TextDB.

the class ExcelSinkTest method testOpen.

@Test
public void testOpen() throws Exception {
    excelSink.open();
    // // verify that inputOperator called open() method
    Mockito.verify(inputOperator).open();
    // // assert that the tuple stream sink removes the _ID and PAYLOAD attribute
    Assert.assertEquals(new Schema(new Attribute("content", AttributeType.TEXT)), excelSink.getOutputSchema());
    excelSink.close();
    Files.deleteIfExists(excelSink.getFilePath());
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) Test(org.junit.Test)

Example 35 with Attribute

use of edu.uci.ics.texera.api.schema.Attribute in project textdb by TextDB.

the class ExcelSinkTest method attributeTypeTest.

@Test
public // writing 10000 tuples
void attributeTypeTest() throws Exception {
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(TestConstants.FIRST_NAME);
    attributeNames.add(TestConstants.LAST_NAME);
    attributeNames.add(TestConstants.AGE);
    attributeNames.add(TestConstants.HEIGHT);
    attributeNames.add(TestConstants.DATE_OF_BIRTH);
    attributeNames.add(TestConstants.DESCRIPTION);
    // Prepare Schema
    Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length];
    for (int count = 0; count < schemaAttributes.length; count++) {
        schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
    }
    // Prepare 10000 tuples as a tupleList
    int testSize = 10000;
    Random rand = new Random();
    List<Tuple> tupleList = new ArrayList<Tuple>();
    for (int i = 0; i < testSize; i++) {
        IField[] fields = { new StringField(getRandomString()), new StringField(getRandomString()), new IntegerField(rand.nextInt()), new DoubleField(rand.nextDouble() * rand.nextInt()), new DateField(getRandomDate()), new TextField(getRandomString()) };
        tupleList.add(new Tuple(new Schema(schemaAttributes), fields));
    }
    assert (tupleList.size() == testSize);
    IOperator inputOperator = Mockito.mock(IOperator.class);
    Mockito.when(inputOperator.getOutputSchema()).thenReturn(new Schema(schemaAttributes));
    OngoingStubbing<Tuple> stubbing = Mockito.when(inputOperator.getNextTuple());
    for (Tuple t : tupleList) {
        stubbing = stubbing.thenReturn(t);
    }
    stubbing = stubbing.thenReturn(null);
    // excel writing test
    excelSink = new ExcelSink(new ExcelSinkPredicate());
    excelSink.setInputOperator(inputOperator);
    excelSink.open();
    excelSink.collectAllTuples();
    excelSink.close();
    Files.deleteIfExists(excelSink.getFilePath());
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) IOperator(edu.uci.ics.texera.api.dataflow.IOperator) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Random(java.util.Random) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Test(org.junit.Test)

Aggregations

Attribute (edu.uci.ics.texera.api.schema.Attribute)98 Test (org.junit.Test)81 Tuple (edu.uci.ics.texera.api.tuple.Tuple)78 ArrayList (java.util.ArrayList)76 Schema (edu.uci.ics.texera.api.schema.Schema)75 IField (edu.uci.ics.texera.api.field.IField)60 StringField (edu.uci.ics.texera.api.field.StringField)56 TextField (edu.uci.ics.texera.api.field.TextField)56 IntegerField (edu.uci.ics.texera.api.field.IntegerField)54 DoubleField (edu.uci.ics.texera.api.field.DoubleField)53 Span (edu.uci.ics.texera.api.span.Span)51 DateField (edu.uci.ics.texera.api.field.DateField)50 SimpleDateFormat (java.text.SimpleDateFormat)47 Dictionary (edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary)28 AttributeType (edu.uci.ics.texera.api.schema.AttributeType)9 IOperator (edu.uci.ics.texera.api.dataflow.IOperator)8 DataflowException (edu.uci.ics.texera.api.exception.DataflowException)6 TexeraException (edu.uci.ics.texera.api.exception.TexeraException)6 List (java.util.List)6 Collectors (java.util.stream.Collectors)5